Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A compiler-blockable algorithm for QR decomposition

Conference ·
OSTI ID:125603
 [1];  [2]
  1. Michigan Technological Univ., Houghton, MI (United States)
  2. Rice Univ., Houston, TX (United States)
Because of an imbalance between computation and memory speed in modern processors, programmers are explicitly restructuring codes to perform well on particular memory systems, leading to machine-specific programs. This paper describes a block algorithm for QR decomposition that is derivable by the compiler and has good performance on small matrices-sizes that are typically run on nodes of a massively parallel system or workstation. The advantage of our algorithm over the one found in LAPACK is that it can be derived by the compiler and needs no hand optimization.
OSTI ID:
125603
Report Number(s):
CONF-950212--; CNN: Grant N00014-91-J-1989; Grant CCR-9120008; Contract TV-ORA4466.01
Country of Publication:
United States
Language:
English

Similar Records

Automatic Blocking Of QR and LU Factorizations for Locality
Conference · Thu Mar 25 23:00:00 EST 2004 · OSTI ID:15013895

Computing rank-revealing QR factorizations of dense matrices.
Journal Article · Mon Jun 01 00:00:00 EDT 1998 · ACM Trans. Math. Software · OSTI ID:937863

A study of the Invariant Subspace Decomposition Algorithm for banded symmetric matrices
Conference · Wed Jun 01 00:00:00 EDT 1994 · OSTI ID:10160866